Ibarrier

Ibarrier#

The benchmark for MPI_Ibarrier that measures communication and computation overlap.

Property

Description

Measuredpattern

MPI_Ibarrier/IMB_cpu_exploit/MPI_Wait

Reportedtimings

  • t_ovrl

  • t_pure

  • t_CPU

  • overlap=100.*max(0,m in(1, (t_pure+t_CPU-t_ovrl) / min(t_pure, t_CPU))

For details, see Measuring Communication and Computation Overlap.

Reportedthroughput

None